Skip to Main content Skip to Navigation
Conference papers

Improving Deep Models of Person Re-identification for Cross-Dataset Usage

Abstract : Person re-identification (Re-ID) is the task of matching humans across cameras with non-overlapping views that has important applications in visual surveillance. Like other computer vision tasks, this task has gained much with the utilization of deep learning methods. However, existing solutions based on deep learning are usually trained and tested on samples taken from same datasets, while in practice one need to deploy Re-ID systems for new sets of cameras for which labeled data is unavailable. Here, we mitigate this problem for one state-of-the-art model, namely, metric embedding trained with the use of the triplet loss function, although our results can be extended to other models. The contribution of our work consists in developing a method of training the model on multiple datasets, and a method for its online practically unsupervised fine-tuning. These methods yield up to 19.1% improvement in Rank-1 score in the cross-dataset evaluation.
Document type :
Conference papers
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01821073
Contributor : Hal Ifip <>
Submitted on : Friday, June 22, 2018 - 11:46:08 AM
Last modification on : Friday, June 22, 2018 - 12:00:38 PM
Long-term archiving on: : Monday, September 24, 2018 - 11:24:24 AM

File

467708_1_En_7_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Sergey Rodionov, Alexey Potapov, Hugo Latapie, Enzo Fenoglio, Maxim Peterson. Improving Deep Models of Person Re-identification for Cross-Dataset Usage. 14th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2018, Rhodes, Greece. pp.75-84, ⟨10.1007/978-3-319-92007-8_7⟩. ⟨hal-01821073⟩

Share

Metrics

Record views

259

Files downloads

1